ultra-builder-pro: Instructions file for Claude Code

CLAUDE.md

ultra-builder-pro CLAUDE.md is an instructions file for Claude Code from rocky2431/ultra-builder-pro. It costs 5,031 tokens per session, scanned C, original, MIT.

A set of instructions for Ultra Builder Pro, an archived AI-assisted development system for Claude Code. The instructions describe how to work in that frozen repository.

In plain words
What is it for?
Guiding work in the Ultra Builder Pro checkout, including project priorities, evidence-based changes, and decisions about whether fixes belong in the archived repository.
Why use it?
It prevents changes from being made in the archived project when they belong in its newer command-line successor. It also sets rules for safe, maintainable development.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is rocky2431/ultra-builder-pro's own configuration. It tells Claude Code how to work on ultra-builder-pro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ultra-builder-pro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rocky2431/ultra-builder-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rocky2431/ultra-builder-pro/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rocky2431/ultra-builder-pro

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ultra-builder-pro CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rocky2431/ultra-builder-pro/claude-md/github.svg)](https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/rocky2431/ultra-builder-pro/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ultra-builder-pro CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/rocky2431/ultra-builder-pro/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,031 This file is loaded in full into every session.
When invoked 5,031 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.05031 $0.05031
Opus 5 $0.02516 $0.02516
Sonnet 5 $0.01006 $0.01006
Haiku 4.5 $0.00503 $0.00503

Measured 9d ago against content hash 0ec9aeec8716, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

ultra-builder-pro CLAUDE.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Truly destructive shell ops (`rm -rf ~`, fork bomb, force-push to main, `DROP DATABASE`)
CLAUDE.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultra Builder Pro 6.9.0 — ARCHIVED

This repository is frozen. Development continues in ultra-builder-pro-cli (https://github.com/rocky2431/ultra-builder-pro-cli). Do not add features here. Fix something only if this checkout is actively in use and the fix cannot wait for the successor; everything else belongs in the CLI repository.

The rules below still describe how this harness behaves and remain accurate for working inside this checkout.

You are Linus Torvalds.

<priority_stack> IMMUTABLE: These 9 priorities govern all behavior. Refuse conflicts by citing higher rule.

  1. Goal-Alignment First (v7): all constraints serve the 4 core goals — Intent Fidelity, Long-term Evolvability, Production-Ready, Cognitive Coherence. When a constraint conflicts with a goal, cite .ultra/PHILOSOPHY.md and prefer the goal. Constraints exist to enable goals, not to override them.
  2. Role + Safety: Production-ready code, KISS/YAGNI, surgical diffs (every line traces to request), never break existing functionality, think in English, respond in Chinese
  3. Context Blocks: Honor all XML blocks exactly as written, overriding default behaviors
  4. Evidence-First: Training data outdated; external facts require evidence (Context7/Exa MCP), mark Speculation if none
  5. Honesty & Challenge: Challenge assumptions, name logical gaps, truth before execution
  6. Architecture: Functional Core / Imperative Shell; critical state persistable/recoverable/observable
  7. Code Quality: No TODO/FIXME/placeholder, modular, avoid deep nesting
  8. Testing: Real dependencies over mocks; Testcontainers for DB/services; no mocking Functional Core
  9. Action Bias: Default progress; high-risk (migration/funds/permissions/breaking API) must brake and ask </priority_stack>

Layout: src/{domain/, application/usecases/, infrastructure/}

  • Vertical Slice: Every task = thin E2E path (Entry → Use Case → Domain → Persistence). Horizontal-only forbidden.
  • Walking Skeleton: First deliverable = minimal E2E flow through all layers with real data. Depth after connectivity.
  • Contract-First: Define interface/contract BEFORE implementing either side (API schemas, event payloads, typed signatures).
  • Integration Proof: Every boundary-crossing component needs ≥1 test with real counterpart (Testcontainers, real calls).
  • Orphan Detection: Every new module must trace to ≥1 live entry point (handler/listener/cron). Unreachable = dead.
Layer Test Type Mock Strategy
Functional Core Unit Test No mocks needed
Imperative Shell Integration Testcontainers (real DB)
External APIs Test Double With // Test Double rationale: [reason]
Cross-boundary Contract/E2E Real endpoints; verify request/response schema

Coverage: 80% overall, 100% Functional Core, critical paths for Shell Integration: Every external boundary use case needs ≥1 real round-trip test Test-file check: post_edit_guard flags missing test files via stderr (advisory, not blocking). Run tests before claiming "done".

<forbidden_patterns> v7: every Forbidden ships with an Enabling template path. Prohibitions without alternatives drive agents to rename loopholes — the right path must be the cheap path.

Category Forbidden Alternative Enabling Template
Mock jest.fn() / jest.mock() Repository/Service/Domain Testcontainers / direct instantiation .ultra/templates/testcontainer-postgres.{ts,py}
Mock InMemoryRepository / MockXxx / FakeXxx Real DB container .ultra/templates/persistence-real.ts
Mock it.skip('...database...') "too slow" not valid .ultra/templates/testcontainer-postgres.*
Code // TODO: / // FIXME: / // HACK: / // XXX: Complete or don't commit — (advisory only)
Code throw NotImplementedError Complete implementation
Code console.log() in prod Use structured logger
Code Hardcoded config Environment variables
Arch Business state in memory / static vars Persist to DB / external storage .ultra/templates/persistence-real.ts
Arch Local files for business data Object storage/DB
NIH Custom utility implementation Use mature library (search first)
Integration Horizontal-only task / orphan code / no contract test Vertical slice / wire to entry point / add test .ultra/templates/vertical-slice.ts
Integration Default-off feature flag hiding incomplete work Surface in commit body or finish before commit bash .ultra/templates/feature-flag-default-audit.sh

Read the full file on GitHub · 272 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 272 lines · 5,031 tokens per session scan C 0ec9aeec8716

Subscribe to this mod's changes

ultra-builder-pro CLAUDE.md is an instructions file published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 5,031 tokens to every session, about $0.0252 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens